Search

Research has shown that climate change creates warmer temperatures and drier conditions, leading to longer wildfire seasons and increased wildfire risks in the United States. These factors have, in turn, led to increases in the frequency, extent, and severity of wildfires in recent years. Given the danger posed by wildland fires to people, property, wildlife, and the environment, there is an urgent need to provide tools for effective wildfire management. Early detection of wildfires is essential to minimizing potentially catastrophic destruction. To that end, in this paper, we present our work on integrating multiple data sources into SmokeyNet, a deep learning model using spatiotemporal information to detect smoke from wildland fires. We present Multimodal SmokeyNet and SmokeyNet Ensemble for multimodal wildland fire smoke detection using satellite-based fire detections, weather sensor measurements, and optical camera images. An analysis is provided to compare these multimodal approaches to the baseline SmokeyNet in terms of accuracy metrics, as well as time-to-detect, which is important for the early detection of wildfires. Our results show that incorporating weather data in SmokeyNet improves performance numerically in terms of both F1 and time-to-detect over the baseline with a single data source. With a time-to-detect of only a few minutes, SmokeyNet can be used for automated early notification of wildfires, providing a useful tool in the fight against destructive wildfires. [ABSTRACT FROM AUTHOR]

The size and frequency of wildland fires in the western United States have dramatically increased in recent years. On high-fire-risk days, a small fire ignition can rapidly grow and become out of control. Early detection of fire ignitions from initial smoke can assist the response to such fires before they become difficult to manage. Past deep learning approaches for wildfire smoke detection have suffered from small or unreliable datasets that make it difficult to extrapolate performance to real-world scenarios. In this work, we present the Fire Ignition Library (FIgLib), a publicly available dataset of nearly 25,000 labeled wildfire smoke images as seen from fixed-view cameras deployed in Southern California. We also introduce SmokeyNet, a novel deep learning architecture using spatiotemporal information from camera imagery for real-time wildfire smoke detection. When trained on the FIgLib dataset, SmokeyNet outperforms comparable baselines and rivals human performance. We hope that the availability of the FIgLib dataset and the SmokeyNet architecture will inspire further research into deep learning methods for wildfire smoke detection, leading to automated notification systems that reduce the time to wildfire response. [ABSTRACT FROM AUTHOR]

Recent thrust-sense deformation in the vicinity of the Main Central Thrust (MCT) zone in the Himalaya of central Nepal can be attributed to tectonics, erosion, or a combination of both. In the same area, contrasting cooling-age patterns in medium- and low-temperature thermochronometers have been interpreted to imply a recent (2.0-0.9 Ma) significant increase in erosional exhumation rates, likely attributable to recent climate changes. No comparable evidence exists for changes in local plate convergence rates. We use numerical models with constant convergence velocity but contrasting erosion rates to show that increased erosion and recent thrusting may be directly connected. In the models, increasing erosivity by a factor of 3 over 3 Ma fundamentally changes the style of deformation, reactivating the dormant model MCT system in the region corresponding to observed thrust faults. The high-erosion model also reproduces the observed cooling-age patterns, whereas the equivalent low-erosion model does not reproduce either observation. Other model predictions, and their implications for the effects of increased erosion on the southern flank of the Himalaya, include: 1) no associated reactivation of normal faulting on the South Tibetan Detachment (STD) system; 2) enhanced upper-crustal extension in the vicinity of the north Himalayan gneiss domes (NHGD); 3) reinvigorated mid-crustal channel flow beneath the NHGD; 4) possible destabilization and wholesale southward flow of the upper crust between the MCT and NHGD, with the potential for catastrophic earthquakes. The first three questions are testable and address the persistent question of the existence and current location of the low-viscosity channel. In particular, the model predicts that it has been stagnant beneath the Tibetan plateau under a relatively low-erosion regime, but has been, or could be, reactivated by more aggressive erosion driven by climate change. The potential for destabilization of the south flank of the orogen has important geological and societal implications. [ABSTRACT FROM AUTHOR]